© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12790
    Prev
    Next
    INDEX
    Explanations

    base64 encoded links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ischen
    0.52
    уса
    0.48
     formatos
    0.47
    iertos
    0.46
    жные
    0.46
    벅
    0.46
     разные
    0.46
     масла
    0.45
    馚
    0.45
    식을
    0.44
    POSITIVE LOGITS
     PDE
    0.47
     Resource
    0.45
     Source
    0.44
     ODE
    0.44
     Lollipop
    0.43
     Mafia
    0.42
     OTC
    0.42
     Amplifier
    0.42
     Honestly
    0.42
     Object
    0.41
    Activations Density 0.009%

    No Known Activations